Skip to content

GLM-5.3-Flash on two CUDA ranks: DFlash2 drafts (--drafter) - #979

Open
BobClawblaw wants to merge 48 commits into
ashhart:mainfrom
BobClawblaw:pr/glm-dflash2
Open

BobClawblaw wants to merge 48 commits into
ashhart:mainfrom
BobClawblaw:pr/glm-dflash2

glm cuda: DFlash2's linears at 4 bits by default (--drafter-bits 4|0)…

70faca3
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning and 1 notice
fmt
succeeded Oct 17, 2026 in 19s